aimeri/spoomplesmaxx-v2.1-30B
LoRA-style vs ibm-granite/granite-4.1-30b-base. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 64 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 192/192, Attention 255/256
2 derivatives checked
- mradermacher/spoomplesmaxx-v2.1-30B-i1-GGUF: Quantization
- mradermacher/spoomplesmaxx-v2.1-30B-GGUF: Quantization